Improving Scene Classification with Weakly Spatial Symmetry

	Improving Scene Classification with Weakly Spatial Symmetry
	Teng, Kezhen; Wang, Jinqiao; Tian, Qi; Lu, Hanqing
	2013
会议名称	ICIP2013
会议录名称	International Conference on Image Processing (ICIP)
页码	3259-3263
会议日期	2013
会议地点	Melbourne, Australia
摘要	The bag-of-visual-words (BOW) model has been widely used in the field of scene classification. Since it ignores the spatial information, the spatial-pyramid-matching (SPM) model [1] was presented by partitioning the image into increasingly fine blocks and computing histograms of local features in each block. However, the spatial symmetry has never been considered explicitly in scene classification as we known. In this paper, a novel descriptor named weakly spatial symmetry (WSS) is proposed to boost the performance of image classification. After region segmentation, the spatial symmetry is represented by L1 distances of region histograms. Four kinds of spatial symmetry are extracted in blocks of increasing scales as in SPM [1]. The WSS descriptor can be used independently or combined with BOW or SPM for scene classification. Experiments on scene-15 and caltech101 dataset demonstrate the effectiveness of the proposed approach.
关键词	Improving Scene Classification
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/4687
专题	紫东太初大模型研究中心_图像与视频分析
通讯作者	Wang, Jinqiao
推荐引用方式 GB/T 7714	Teng, Kezhen,Wang, Jinqiao,Tian, Qi,et al. Improving Scene Classification with Weakly Spatial Symmetry[C],2013:3259-3263.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Improving scene clas（462KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载